Update README.md

README.md

@@ -33,18 +33,30 @@ The overall performance of model on QA **test**:
 training args:
 
 ```
-{"per_device_train_batch_size": 8, "per_device_eval_batch_size": 8, "per_gpu_train_batch_size": null, "per_gpu_eval_batch_size": null, "gradient_accumulation_steps": 1, "eval_accumulation_steps": null, "eval_delay": 0,
-"learning_rate": 2e-05, "weight_decay": 0.0, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1.0,
-"num_train_epochs": 10.0, "max_steps": -1, "lr_scheduler_type": "linear", "warmup_ratio": 0.0, "warmup_steps": 50, "log_level": "passive",
-"log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "outputs-ziya-llama-13b-sft-med-v2/logs", "logging_strategy": "steps",
-"logging_first_step": false, "logging_steps": 50, "logging_nan_inf_filter": true, "save_strategy": "steps", "save_steps": 50,
-"save_total_limit": 3, "save_safetensors": false, "save_on_each_node": false, "no_cuda": false, "use_mps_device": false, "seed": 42,
-"data_seed": null, "jit_mode_eval": false, "use_ipex": false, "bf16": false, "fp16": true, "fp16_opt_level": "O1",
-"half_precision_backend": "cuda_amp", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": null, "local_rank": 0, "xpu_backend": null, "tpu_num_cores": null, "tpu_metrics_debug": false, "debug": [], "dataloader_drop_last": false,
-"eval_steps": 50, "dataloader_num_workers": 0, "past_index": -1, "run_name": "outputs-ziya-llama-13b-sft-med-v2", "disable_tqdm": false, "remove_unused_columns": false, "label_names": null, "load_best_model_at_end": true, "metric_for_best_model": "loss", "greater_is_better": false, "ignore_data_skip": false, "sharded_ddp": [], "fsdp": [], "fsdp_min_num_params": 0,
-"fsdp_config": { "fsdp_min_num_params": 0, "xla": false, "xla_fsdp_grad_ckpt": false }, "fsdp_transformer_layer_cls_to_wrap": null,
-"deepspeed": null, "label_smoothing_factor": 0.0, "optim": "adamw_torch", "optim_args": null, "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": [ "tensorboard" ], "ddp_find_unused_parameters": false, "ddp_bucket_cap_mb": null, "dataloader_pin_memory": true,
-"skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": false, "resume_from_checkpoint": null, "hub_model_id": null, "hub_strategy": "every_save", "hub_token": "<hub_token>", "hub_private_repo": false, "gradient_checkpointing": false, "include_inputs_for_metrics": false, "fp16_backend": "auto", "push_to_hub_model_id": null, "push_to_hub_organization": null, "push_to_hub_token": "<push_to_hub_token>", "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": null, "ray_scope": "last", "ddp_timeout": 1800, "torch_compile": false, "torch_compile_backend": null, "torch_compile_mode": null }
+{"per_device_train_batch_size": 8,
+"per_device_eval_batch_size": 8,
+"gradient_accumulation_steps": 1, 
+"learning_rate": 2e-05, 
+"num_train_epochs": 10.0,
+"max_steps": -1,
+"lr_scheduler_type": "linear",
+"warmup_ratio": 0.0,
+"warmup_steps": 50, 
+"save_strategy": "steps",
+"save_steps": 500,
+"save_total_limit": 13,
+"seed": 42,
+"bf16": false,
+"fp16": true, 
+"eval_steps": 50,
+"remove_unused_columns": false,
+"load_best_model_at_end": true,
+"metric_for_best_model": "loss", 
+"optim": "adamw_torch",
+"report_to": [ "tensorboard" ], 
+"ddp_timeout": 1800,
+"torch_compile": false
+}
 ```
 
 train loss: